Profile Job Results
Jobs
j5qrd7qnp
Results Ready
Name
swin_small
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
9/13/2025, 10:45:12 PM
Options
--qairt_version 2.36Versions
- ONNX Runtime: 1.22.2
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.09.05.0
Estimated Inference Time
343 ms
Estimated Peak Memory Usage
66 ‑ 92 MB
Compute Units
CPU
2672
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.63 s | 96‑107 MB |
Subsequent App Load | 4.66 s | 74‑114 MB |
Inference | 343 ms | 66‑92 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
Sign up to run this model on a hosted Qualcomm® device!
Run on device